© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 29156
    Prev
    Next
    INDEX
    Explanations

    conjunctions and phrases that link concepts together

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    cul
    -0.07
    ConverterFactory
    -0.07
    rieve
    -0.07
    ystal
    -0.06
    ldr
    -0.06
    achen
    -0.06
    UMP
    -0.06
    à¸Īะà¸ķ
    -0.06
    rossover
    -0.06
    VD
    -0.06
    POSITIVE LOGITS
     thereby
    0.12
     pÅĻitom
    0.07
     thus
    0.07
     resultat
    0.07
     damit
    0.07
    çµIJæŀľ
    0.07
    ç»ĵæŀľ
    0.07
     Doing
    0.06
     Result
    0.06
     Outcome
    0.06
    Activations Density 0.052%

    No Known Activations